README.md

---
license: apache-2.0
tags:
- setfit
- sentence-transformers
- text-classification
pipeline_tag: text-classification
datasets:
- librarian-bots/dataset_abstracts
language:
- en
---

# librarian-bots/is_new_dataset_student_model

This is a [SetFit model](https://github.com/huggingface/setfit) that can be used for text classification. The model is trained to predict whether a title + abstract for a paper on arXiv introduces a new dataset. 
The model was trained on Arxiv papers returned from the search `dataset`. The model, therefore, aims to disambiguate papers about datasets vs papers which introduce a new dataset. 
This model was trained through distillation training using a larger model [`librarian-bots/is_new_dataset_teacher_model`](https://huggingface.co/librarian-bots/is_new_dataset_teacher_model). 

## Usage

To use this model for inference, first install the SetFit library:

```bash
python -m pip install setfit
```

You can then run inference as follows:

```python
from setfit import SetFitModel

# Download from Hub and run inference
model = SetFitModel.from_pretrained("librarian-bots/is_new_dataset_student_model")
# Run inference
preds = model([Abstract + Title])
```

During model training, the text was formatted using the following format: 

```
TITLE: title text
ABSTRACT: abstract text
```

You probably want to use the same format when running inference for this model.  


## BibTeX entry and citation info

To cite the SetFit approach used to train this model, please use this citation:

```bibtex
@article{https://doi.org/10.48550/arxiv.2209.11055,
doi = {10.48550/ARXIV.2209.11055},
url = {https://arxiv.org/abs/2209.11055},
author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Efficient Few-Shot Learning Without Prompts},
publisher = {arXiv},
year = {2022},
copyright = {Creative Commons Attribution 4.0 International}
}
```